ML Anthology

Segmentation for Robust Tracking in the Presence of Severe Occlusion

Camillo Gentile, Octavia I. Camps, Mario Sznaier
CVPR 2001 pp. II:483-488
doi:10.1109/CVPR.2001.991001 /cvpr/2001/gentile2001cvpr-segmentation/

Abstract

Tracking an object in a sequence of images can fail due to partial occlusion or clutter Robustness can be increased by tracking a set of "parts", provided that a suitable set can be identified. In this paper we propose a novel segmentation, specifically designed to improve robustness against occlusion in the context of tracking. The main result shows that tracking the parts resulting from this segmentation outperforms both tracking parts obtained through traditional segmentations, and tracking the entire target. Additional results include a statistical analysis of the correlation between features of a part and tracking error, and identifying a cost function highly correlated with the tracking error.

CVPR Semantic Scholar

Cite

Text

Gentile et al. "Segmentation for Robust Tracking in the Presence of Severe Occlusion." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001. doi:10.1109/CVPR.2001.991001

Markdown

[Gentile et al. "Segmentation for Robust Tracking in the Presence of Severe Occlusion." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001.](https://mlanthology.org/cvpr/2001/gentile2001cvpr-segmentation/) doi:10.1109/CVPR.2001.991001

BibTeX

@inproceedings{gentile2001cvpr-segmentation,
  title     = {{Segmentation for Robust Tracking in the Presence of Severe Occlusion}},
  author    = {Gentile, Camillo and Camps, Octavia I. and Sznaier, Mario},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2001},
  pages     = {II:483-488},
  doi       = {10.1109/CVPR.2001.991001},
  url       = {https://mlanthology.org/cvpr/2001/gentile2001cvpr-segmentation/}
}